Lab
AI tools, creative workflows, developer deep-dives, and behind-the-scenes from RAXXO Studios.
7 articles
Claude Security: Anthropic's New Vulnerability Scanner
Anthropic shipped Claude Security in beta, a multi-agent scanner that turns vulnerability findings into reviewed patches inside Claude Code.
Read articleClaude Security Update: Scans, Webhooks, 6 Partners
Claude Security left its launch behind with scheduled scans, directory targeting, and CSV or Markdown exports. Slack and Jira webhooks plus dismissals that stick turn...
Claude Security Goes Public Beta: Repo Scanning, Vuln Explainer, Patch Guidance
Claude Security entered public beta on May 2026, scanning repos and explaining vulnerabilities for Claude Enterprise customers only Three core capabilities ship now: full repo...
Shopify April 2026 Breaking Changes: What Developers Must Fix
Shopify now requires expiring offline access tokens for all new public apps as of April 1 Partner organizations must use role-based access control for all...
GitHub Got Hit With 475 Malicious PRs in 26 Hours
Attacker opened 475+ malicious PRs across GitHub in 26 hours using AI-generated payloads The campaign exploited pull_request_target workflow triggers in GitHub Actions Wiz tracked 6...
Anthropic Just Gave 12 Companies Their Most Dangerous AI Model. On Purpose.
Project Glasswing uses Claude Mythos Preview to find zero-days in critical infrastructure. 12 partners, 100M USD in credits, and bugs older than most interns.
How I Built an Anti-Cheat System for a CSS Game
Three versions of anti-cheat for a CSS centering game with 3,000+ attempts. HMAC tokens, pattern analysis, and HTTP 418 teapots.